|
一种基于机器学习的在线学习行为投入评测模型
|
Abstract:
疫情期间在线学习平台迅速爆增,学习者也越来越多,但是在线学习的监督性、学习者的投入度、学习的评估等因素,从而影响了学习者的学习效果。随着学习分析技术和教育数据挖掘的融合应用,文章通过分析学习者的在线学习行为投入数据,采用在线学习平台下对学习者行为投入及时评估的方法,构建一种基于机器学习的在线学习行为投入评测模型。该模型以在线学习者的投入度为评估目的,通过机器学习算法对学习者的投入度进行分析,帮助学习者及时自我调整,也帮助施教者更好地开展教学。
During the epidemic, online learning platforms have exploded rapidly, and there are more and more learners. However, factors such as the supervision of online learning, the degree of learner engagement, and the evaluation of learning affect the learning effect of learners. With the integration and application of learning analysis technology and educational data mining, this paper constructs an online learning behavior based on machine learning by analyzing the online learning behavior input data of learners, and adopting the method of timely assessment of learner behavior input under the online learning platform. The input evaluation model uses the online learner’s engagement as the evaluation purpose, and analyzes the learner’s engagement through the machine learning algorithm, which helps the learners to adjust themselves in time, and also helps the teachers to carry out better teaching.
[1] | Dai, X.L., Guo, K. and Liu, L. (2017) Empirical Research on Factors Affecting the MOOC Learners Satisfaction-Based Structural Equation Anal. MOOC Learners Universities China. Moderm DistanceEducation, 212, 17-23. |
[2] | Wong, K.M. (2020) “A Design Framework for Enhancing Engagement in Student-Centered Learning: Own It, Learn It, and Share It” by Lee and Hannafin (2016): An International Perspective. Educational Technology Research and Development, 69, 93-96. https://doi.org/10.1007/s11423-020-09842-w |
[3] | Lee, J., Song, H. and Hong, A. (2019) Exploring Factors, and Indicators for Measuring Students’ Sustainable Engagement in e-Learning. Sustainability, 11, Article No. 985. https://doi.org/10.3390/su11040985 |
[4] | Cox, D.H. and Belbin, B. (2020) Student Services at a Distance. In: Cox, D.H. and Strange, C.C., Eds., Achieving Student Success: Effective Student Services in Canadian Higher Education, McGill-Queen’s University Press, Montreal, 221-230. https://doi.org/10.1515/9780773575721-018 |
[5] | Gregori, E.B., Zhang, J., Galvan-Fernandez, C. and De Asis Fermnandez-Navarro, F. (2018) Learner Support in MOOCs: Iden-tifying Variables Linked to Completion. Computers & Education, 122, 153-168.
https://doi.org/10.1016/j.compedu.2018.03.014 |
[6] | 黄寿孟, 夏王霞. 基于LBSN中锚链接方法的链路预测模型[J]. 海南热带海洋学院学报, 2021(5): 72-77. |
[7] | 黄寿孟, 夏王霞. 一种基于LSH技术的链路预测方法[J]. 信息记录材料, 2021, 22(7): 139-142. |
[8] | 黄寿孟. 一种基于监督学习的异构网链路预测模型[J]. 计算机科学, 2021, 48(S2): 111-116. |
[9] | 黄寿孟. 一种基于节点路径信息相似性的预测方法[J]. 海南师范大学学报(自然科学版), 2022, 35(1): 25-30. |
[10] | 黄寿孟. 基于超网络模型的混合教学知识传播研究[J]. 信息与电脑(理论版), 2019(5): 37-39. |
[11] | 黄寿孟. 一种基于代价的XML查询优化操作模型[J]. 计算机科学, 2016, 43(S2): 529-531. |
[12] | 黄寿孟. 基于Flex的数据通信技术研究与应用[J]. 中国现代教育装备, 2016(17): 12-15. |
[13] | 黄寿孟, 高华玲, 潘玉霞. 软件相似性分析算法的研究综述[J]. 计算机科学, 2016, 43(S1): 467-470. |
[14] | 冯淑娟, 黄寿孟. 跨源多维政务数据治理综述[J]. 网络安全和信息化, 2021(11): 76-79. |
[15] | 黄寿孟, 马莲姑. 基于深度学习的混合教学评价体系研究[J]. 甘肃广播电视大学学报, 2022, 32(1): 38-44. |
[16] | 黄寿孟, 赵福军, 李海军, 等. 基于区块链的政务数据共享平台设计[J]. 电脑编程技巧与维护, 2022(9): 91-93. |
[17] | 黄寿孟, 冯淑娟, 韩强. 基于大数据平台的政务数据治理体系研究[J]. 电脑编程技巧与维护, 2022(10): 103-105. |
[18] | 黄寿孟, 韩强, 冯淑娟. 一种基于健康医疗大数据的智能治理系统[J]. 现代信息科技, 2023, 7(1): 14-17. |
[19] | 黄寿孟, 刘小飞, 韩强, 等. 基于微信小程序的计算机类课程教学平台的设计及应用[J]. 现代计算机, 2023, 29(8): 104-107. |
[20] | 黄寿孟, 刘小飞, 韩强, 等. 基于微信小程序的计算机类课程混合式教学设计及应用[J]. 现代信息科技, 2023, 7(11): 186-189. |